See the workshop program for presentation times.

• A Scrambled Positional Encoding Is Worse Than None PDF
  Srinivas Harish
• Autoregressive vs. Diffusion Language Models for Clinical Text Summarisation PDF
  Carlos A. Conde Giron, Zexuan Li, Robert A. Bagheri, Ruurd J. A. Kuiper
• Does SAM Pay Off? A Cost-Adjusted Analysis of Sharpness-Aware Pretraining PDF
  Ivan Maksimov, Joqsan Azocar, Vasily Konovalov
• From Found to Designed: Concepts as a Design Axis for Large Language Models PDF
  Chen Shani
  Invited paper
• Reconstructing Locality-Disrupted Text: Effects of Architecture and Scale PDF
  Evelien van Driel, Amirhossein Mohammadi, Robert A. Bagheri
• Scan Order Is a Reasoning Prior: Geometry-Aware Multi-Directional Mamba-2 for Tiny Recursive Reasoning PDF
  Zhenxuan Yu
• Small Encoder-Decoders as Tool-Calling Backbones: A Capability Decomposition at 270M–1B PDF
  Sergey Pletenev